An Improvement In The Moment-Preserving Thresholding Method

[[abstract]]Thresholding is frequently used for image segmentation. One of the most popular approach to thresholding is the moment-preserving thresholding method proposed by Tsai in 1985. However, it does not work well when the peaks of a histogram have a great size variation. Hence in this study we propose a simple and effective improvement in Tsai’s method such that suitable thresholds can be found even when the histogram has peaks with a great size variation. In the proposed method, the fractions of below-threshold and above-threshold pixels and their represented gray values are first computed by Tsai’s moment-preserving thresholding method. They are next used to simulate shapes of peaks in the histogram of the input image. Then the thresholds are determined based on the locations of the simulated peaks. Experimental results show the effectiveness of the proposed improvement